{"id":"https://openalex.org/W2395825834","doi":"https://doi.org/10.1109/icassp.2016.7472694","title":"Parallelizing WFST speech decoders","display_name":"Parallelizing WFST speech decoders","publication_year":2016,"publication_date":"2016-03-01","ids":{"openalex":"https://openalex.org/W2395825834","doi":"https://doi.org/10.1109/icassp.2016.7472694","mag":"2395825834"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2016.7472694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034476447","display_name":"Charith Mendis","orcid":"https://orcid.org/0000-0002-8140-2321"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Charith Mendis","raw_affiliation_strings":["Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012153296","display_name":"Jasha Droppo","orcid":"https://orcid.org/0000-0001-6097-0090"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jasha Droppo","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077514991","display_name":"Saeed Maleki","orcid":"https://orcid.org/0000-0003-1107-1827"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Saeed Maleki","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040009052","display_name":"Madanlal Musuvathi","orcid":"https://orcid.org/0000-0002-2482-7892"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Madanlal Musuvathi","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013212213","display_name":"Todd Mytkowicz","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Todd Mytkowicz","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069954850","display_name":"Geoffrey Zweig","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Geoffrey Zweig","raw_affiliation_strings":["Microsoft Research"],"affiliations":[{"raw_affiliation_string":"Microsoft Research","institution_ids":["https://openalex.org/I4210164937"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5034476447"],"corresponding_institution_ids":["https://openalex.org/I63966007"],"apc_list":null,"apc_paid":null,"fwci":5.1417,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.9567533,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5325","last_page":"5329"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9979000091552734,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8882288932800293},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6405627131462097},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.620047926902771},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5637848973274231},{"id":"https://openalex.org/keywords/viterbi-decoder","display_name":"Viterbi decoder","score":0.5278377532958984},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5100591778755188},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.49029281735420227},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4843803346157074},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.46087318658828735},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.44196629524230957},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.42926907539367676},{"id":"https://openalex.org/keywords/precomputation","display_name":"Precomputation","score":0.42309531569480896},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.42105287313461304},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.34572693705558777},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3303174078464508},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.29962629079818726},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.2767708897590637},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22766682505607605},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10860922932624817}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8882288932800293},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6405627131462097},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.620047926902771},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5637848973274231},{"id":"https://openalex.org/C117379686","wikidata":"https://www.wikidata.org/wiki/Q6996459","display_name":"Viterbi decoder","level":3,"score":0.5278377532958984},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5100591778755188},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.49029281735420227},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4843803346157074},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.46087318658828735},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.44196629524230957},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.42926907539367676},{"id":"https://openalex.org/C159379195","wikidata":"https://www.wikidata.org/wiki/Q7239568","display_name":"Precomputation","level":3,"score":0.42309531569480896},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.42105287313461304},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.34572693705558777},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3303174078464508},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.29962629079818726},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.2767708897590637},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22766682505607605},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10860922932624817},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2016.7472694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2016.7472694","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W167388389","https://openalex.org/W1557273125","https://openalex.org/W1977755381","https://openalex.org/W2016559894","https://openalex.org/W2037102844","https://openalex.org/W2113563476","https://openalex.org/W2136939588","https://openalex.org/W2138234674","https://openalex.org/W2153989825","https://openalex.org/W2160688560","https://openalex.org/W2160815625","https://openalex.org/W2168339347","https://openalex.org/W2181607856","https://openalex.org/W2184045248","https://openalex.org/W2333081718","https://openalex.org/W2396659748","https://openalex.org/W4230609379","https://openalex.org/W4230995274","https://openalex.org/W6702638944","https://openalex.org/W6712446967"],"related_works":["https://openalex.org/W2102309991","https://openalex.org/W2560896464","https://openalex.org/W1795315578","https://openalex.org/W2373954783","https://openalex.org/W2133857928","https://openalex.org/W2143297499","https://openalex.org/W2535886977","https://openalex.org/W2356694334","https://openalex.org/W2991144886","https://openalex.org/W2790444905"],"abstract_inverted_index":{"The":[0,42],"performance-intensive":[1],"part":[2],"of":[3,17,115],"a":[4,59,69,82,93,98,112],"large-vocabulary":[5],"continuous":[6],"speech-recognition":[7],"system":[8],"is":[9,45],"the":[10,15,25,48],"Viterbi":[11],"computation":[12,50],"that":[13,19],"determines":[14],"sequence":[16],"words":[18],"are":[20],"most":[21],"likely":[22],"to":[23,46,53],"generate":[24],"acoustic-state":[26],"scores":[27],"extracted":[28],"from":[29,121],"an":[30,36,86],"input":[31],"utterance.":[32],"This":[33],"paper":[34],"presents":[35],"efficient":[37],"parallel":[38],"algorithm":[39],"for":[40],"Viterbi.":[41],"key":[43],"idea":[44],"partition":[47],"per-frame":[49],"among":[51],"threads":[52],"minimize":[54],"inter-thread":[55],"communication":[56],"despite":[57],"traversing":[58],"large":[60],"irregular":[61],"acoustic":[62],"and":[63,77,97],"language":[64],"model":[65],"graphs.":[66],"Together":[67],"with":[68],"per-thread":[70],"beam":[71],"search,":[72],"load":[73],"balancing":[74],"language-model":[75],"lookups,":[76],"memory":[78],"optimizations,":[79],"we":[80],"achieve":[81],"6.67x":[83],"speedup":[84],"over":[85],"highly-optimized":[87],"production-quality":[88],"WFST-based":[89],"speech":[90],"decoder.":[91],"On":[92],"200,000":[94],"word":[95],"vocabulary":[96],"59":[99],"million":[100],"ngram":[101],"model,":[102],"our":[103],"decoder":[104],"runs":[105],"at":[106],"0.27x":[107],"real":[108],"time":[109],"while":[110],"achieving":[111],"word-error":[113],"rate":[114],"14.81%":[116],"on":[117],"6214":[118],"labeled":[119],"utterances":[120],"Voice":[122],"Search":[123],"data.":[124]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}